How does one find top k embedding vectors such that they are similar to...

distro_dave

Given vector A and vector B, which would be the better approach for getting top k embedding vectors such that they are similar to embedding vector A and dissimilar to vector B. Approach 1: calculate f(V) = cosine_similarity(A,V) - cosine_similarity(B,V) for each vector V sort vectors by f(V) value in descending order take first k of them. Approach 2: calculate f(V) = cosine_similarity(A,V) , g(V) = cosine_similarity(B,V) for each vector V sort...

Originally asked by Shubham on Stack Exchange (ai) (CC BY-SA 4.0).

Variant 65.

uphilltech

Great question — answering as the UphillTech team:

As the objective is to find the most similar to A and disimilar Vector to B approach 2 would be the most appropriate. Why not Approach 1: It can lead to confusing results. If you look at the example below multiple scenarios lead to same final value. This may lead to few problems : For same output how do you know which vector should be preferred Subtracting with each other may cancel out impact of dissimilarity on one with other Why not Approach 3: Vector Subtraction is not commutative . So you will get different results based on whether you use A first or B first. Moreover lets see an example where it fails completely : Suppose we have 2 dimension vector A and B, and we want to vector V...

Full answer by Ashwiniku918: https://ai.stackexchange.com/a/34074 (CC BY-SA 4.0).

Want it for your business? UphillTech.